# Datost

> Datost is a proactive AI data analyst that continuously watches the data, accounts, and metrics that matter to each person on your team — surfacing the issue, the fix, and the opportunity before anyone asks. It scores 75.2% on BIRD-Interact, the hardest text-to-SQL benchmark, versus 33% for the same frontier model alone.

This file is generated from the site's source content. It is a curated index for AI assistants, not a crawler permissions file. For crawler permissions, see `/robots.txt`.

## Core Pages

- [Home](https://datost.com/): The proactive AI data analyst that surfaces what matters before anyone asks.
- [Why Datost](https://datost.com/why): The case for a proactive, always-on analyst over reactive dashboards.
- [Features](https://datost.com/features): What Datost does and how it connects to your data.
- [Security](https://datost.com/security): How Datost handles data, access, and compliance.

## Comparisons

- [Datost vs Hex](https://datost.com/vs/hex)
- [Datost vs Mode](https://datost.com/vs/mode)
- [Datost vs Metabase](https://datost.com/vs/metabase)
- [Datost vs Julius](https://datost.com/vs/julius)
- [Datost vs Sigma](https://datost.com/vs/sigma)
- [Datost vs Numerous AI](https://datost.com/vs/numerous-ai)
- [Datost vs Snowflake Cortex Analyst](https://datost.com/vs/snowflake-cortex-analyst)

## Glossary

- [Text-to-SQL](https://datost.com/glossary/text-to-sql): Text-to-SQL is the task of translating a natural-language question into a SQL query that runs against a database and returns the answer.
- [Conversational Analytics](https://datost.com/glossary/conversational-analytics): Conversational analytics is the practice of getting answers from your data by asking questions in plain language and receiving numbers, charts, or explanations back, instead of building a dashboard or writing SQL yourself.
- [Semantic Layer](https://datost.com/glossary/semantic-layer): A semantic layer is a central definition store that maps human-readable business concepts (revenue, churn, MRR) to the underlying tables and SQL that compute them.
- [Metric Definition](https://datost.com/glossary/metric-definition): A metric definition is the exact SQL or calculation that produces a business metric, plus the documented assumptions behind it.
- [Agent Memory](https://datost.com/glossary/agent-memory): Agent memory is the system that lets an AI agent persist what it learns — corrections, patterns, definitions, and business context — across conversations, so it stops repeating mistakes and gets your business right over time.
- [Data Warehouse vs Data Lake](https://datost.com/glossary/data-warehouse-vs-data-lake): A data warehouse stores structured, query-ready tables for analytics. A data lake stores raw files in any format. Modern stacks usually have both.
- [BIRD-Interact](https://datost.com/glossary/bird-interact): BIRD-Interact is a text-to-SQL benchmark of 600 deliberately ambiguous business questions across 22 realistic Postgres databases, published at ICLR 2026.
- [RAG (Retrieval-Augmented Generation)](https://datost.com/glossary/rag): RAG is a pattern where an AI system retrieves relevant context from a knowledge source before generating an answer, instead of relying only on the model's training data.
- [Cohort Analysis](https://datost.com/glossary/cohort-analysis): Cohort analysis groups users by when they started (or another shared trait) and measures how that group behaves over time, so trends are not muddied by mixing new and old users.
- [ARR (Annual Recurring Revenue)](https://datost.com/glossary/arr): ARR is the annualized value of all active recurring subscriptions at a point in time: what you would book over the next year if nothing changed.
- [Retention Curve](https://datost.com/glossary/retention-curve): A retention curve plots, for a cohort of users, what fraction is still active at each point in time after they joined.
- [Activation Funnel](https://datost.com/glossary/activation-funnel): The activation funnel measures how new users progress from signup through the steps that predict long-term retention, and where they drop off.
- [Attribution Model](https://datost.com/glossary/attribution-model): An attribution model assigns credit for a conversion (signup, purchase, deal) to the marketing touchpoints that preceded it.
- [Column Lineage](https://datost.com/glossary/column-lineage): Column lineage traces, for any column in any table, the chain of upstream columns and transformations that produced it.

## Research

- [We stopped guessing how good Datost was (BIRD-Interact)](https://datost.com/blog/bird-interact): Datost scores 75.2% on BIRD-Interact, the hardest text-to-SQL benchmark — the same frontier model scores 33% alone.

## Discovery

- [Sitemap](https://datost.com/sitemap-index.xml): Complete search-engine sitemap, if available.
- [Robots policy](https://datost.com/robots.txt): Crawler permissions for automated agents.